Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 14 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1060626 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.8278. Min Act: -0.0000

Data Index: 722686 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7331. Min Act: -0.0000

Data Index: 168151 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7204. Min Act: -0.0000

Data Index: 683953 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7256. Min Act: -0.0000

Data Index: 98451 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7231. Min Act: -0.0000

Data Index: 938670 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1314275 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1195162 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1341527 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7495. Min Act: -0.0000

Data Index: 126113 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6798. Min Act: -0.0000

Data Index: 167301 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6683. Min Act: -0.0000

Data Index: 44912 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1193568 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6470. Min Act: -0.0000

Data Index: 500826 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6885. Min Act: -0.0000

Data Index: 529176 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7037. Min Act: -0.0000

Data Index: 863951 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1387955 (Python Code)

Max Activating Token Index: 991

Text #17

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6875. Min Act: -0.0000

Data Index: 397562 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6821. Min Act: -0.0000

Data Index: 94824 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1166502 (C4 (Web Text))

Max Activating Token Index: 848